{"id":"https://openalex.org/W3035912249","doi":"https://doi.org/10.1145/3434073.3444667","title":"Feature Expansive Reward Learning","display_name":"Feature Expansive Reward Learning","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3035912249","doi":"https://doi.org/10.1145/3434073.3444667","mag":"3035912249"},"language":"en","primary_location":{"id":"doi:10.1145/3434073.3444667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434073.3444667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434073.3444667","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3434073.3444667","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034978137","display_name":"Andreea Bobu","orcid":"https://orcid.org/0000-0002-9507-7427"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreea Bobu","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083812172","display_name":"Marius Wiggert","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marius Wiggert","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Tomlin","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anca D. Dragan","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47497752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7067348957061768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6863995790481567},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.677085280418396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6585249304771423},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6483706831932068},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6234592199325562},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5772870779037476},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.49767497181892395},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.47928398847579956},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4773297905921936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46105754375457764},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4240749180316925},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42022061347961426},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41376766562461853},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2237951159477234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1357041895389557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13497218489646912}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7067348957061768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863995790481567},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.677085280418396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6585249304771423},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6483706831932068},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6234592199325562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5772870779037476},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.49767497181892395},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.47928398847579956},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4773297905921936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46105754375457764},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4240749180316925},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42022061347961426},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41376766562461853},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2237951159477234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1357041895389557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13497218489646912},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3434073.3444667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434073.3444667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434073.3444667","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3434073.3444667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434073.3444667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434073.3444667","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2625273505","display_name":null,"funder_award_id":"20-1-2736","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G402934692","display_name":null,"funder_award_id":"FA9550-17-1-0308","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035912249.pdf","grobid_xml":"https://content.openalex.org/works/W3035912249.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1540637571","https://openalex.org/W1594849649","https://openalex.org/W1837766154","https://openalex.org/W2098774185","https://openalex.org/W2117675763","https://openalex.org/W2126105931","https://openalex.org/W2157289187","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2177382477","https://openalex.org/W2293883387","https://openalex.org/W2319178748","https://openalex.org/W2410842990","https://openalex.org/W2549684528","https://openalex.org/W2763110165","https://openalex.org/W2767734520","https://openalex.org/W2769520592","https://openalex.org/W2792089292","https://openalex.org/W2890752237","https://openalex.org/W2953494151","https://openalex.org/W2953931148","https://openalex.org/W2962937807","https://openalex.org/W2962943921","https://openalex.org/W2962951365","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W2963731007","https://openalex.org/W2994972935","https://openalex.org/W2995356893","https://openalex.org/W3027397596","https://openalex.org/W3027820740","https://openalex.org/W3106171760"],"related_works":["https://openalex.org/W8539471","https://openalex.org/W1323832","https://openalex.org/W9942637","https://openalex.org/W7430954","https://openalex.org/W4085024","https://openalex.org/W8698196","https://openalex.org/W929682","https://openalex.org/W13926559","https://openalex.org/W5991403","https://openalex.org/W12783365"],"abstract_inverted_index":{"When":[0,42],"a":[1,8,11,70,110,192,201,206],"person":[2,119],"is":[3,80,106,130,137],"not":[4],"satisfied":[5],"with":[6,191],"how":[7],"robot":[9,24,62,93,122,195],"performs":[10],"task,":[12],"they":[13,37],"can":[14],"intervene":[15],"to":[16,25,133],"correct":[17],"it.":[18],"Reward":[19],"learning":[20,85,144],"methods":[21],"enable":[22],"the":[23,43,61,74,87,92,118,121,126,145,148,156,161,165,177,181],"adapt":[26],"its":[27],"reward":[28,71,157,179],"function":[29],"online":[30],"based":[31],"on":[32,39,164],"such":[33],"human":[34,114,162],"input,":[35],"but":[36],"rely":[38],"handcrafted":[40],"features.":[41],"correction":[44],"cannot":[45],"be":[46],"explained":[47],"by":[48],"these":[49],"features,":[50],"recent":[51],"work":[52],"in":[53,116,189,200,205],"deep":[54,183],"Inverse":[55],"Reinforcement":[56],"Learning":[57],"(IRL)":[58],"suggests":[59],"that":[60,81,99],"could":[63],"ask":[64,96],"for":[65,97,143],"task":[66],"demonstrations":[67],"and":[68,152,173],"recover":[69],"defined":[72],"over":[73,180],"raw":[75,149],"state":[76,150],"space.":[77],"Our":[78],"insight":[79],"rather":[82],"than":[83],"implicitly":[84],"about":[86,103],"missing":[88,166],"feature(s)":[89],"from":[90,123,147],"demonstrations,":[91],"should":[94],"instead":[95],"data":[98],"explicitly":[100],"teaches":[101],"it":[102,105,136,154],"what":[104],"missing.":[107],"We":[108,139,186],"introduce":[109],"new":[111],"type":[112],"of":[113,176],"input":[115,163],"which":[117],"guides":[120],"states":[124,134],"where":[125,135],"feature":[127,146],"being":[128],"taught":[129],"highly":[131],"expressed":[132],"not.":[138],"propose":[140],"an":[141],"algorithm":[142],"space":[151],"integrating":[153],"into":[155],"function.":[158],"By":[159],"focusing":[160],"feature,":[167],"our":[168],"method":[169],"decreases":[170],"sample":[171],"complexity":[172],"improves":[174],"generalization":[175],"learned":[178],"above":[182],"IRL":[184],"baseline.":[185],"show":[187],"this":[188],"experiments":[190],"physical":[193],"7DOF":[194],"manipulator,":[196],"as":[197,199],"well":[198],"user":[202],"study":[203],"conducted":[204],"simulated":[207],"environment.":[208]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-06-25T00:00:00"}